{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:24:09Z","timestamp":1777890249317,"version":"3.51.4"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01900","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20435-20444","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Simple Edits: Composed Video Retrieval with Dense Modifications"],"prefix":"10.1109","author":[{"given":"Omkar","family":"Thawakar","sequence":"first","affiliation":[{"name":"Mohamed bin Zayed University of AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dmitry","family":"Demidov","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ritesh","family":"Thawkar","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rao Muhammad","family":"Anwer","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mubarak","family":"Shah","sequence":"additional","affiliation":[{"name":"University of Central Florida"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fahad Shahbaz","family":"Khan","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Salman","family":"Khan","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of AI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3593539"},{"key":"ref2","article-title":"A clip-hitchhiker\u2019s guide to long video retrieval","author":"Bain","year":"2022","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"ref7","article-title":"Artemis: Attention-based retrieval with text-explicit matching and implicit similarity","author":"Delmas","year":"2022","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Modality-agnostic attention fusion for visual search with text feedback","author":"Dodds","year":"2020","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01371"},{"key":"ref11","article-title":"Compodiff: Versatile composed image retrieval with latent diffusion","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72913-3_1"},{"key":"ref13","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","first-page":"7","article-title":"Trace: Transform aggregate and compose visiolinguistic representations for image search with text feedback","volume":"7","author":"Jandial","year":"2020","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00067"},{"key":"ref16","article-title":"Vision-by-language for training-free compositional image retrieval","author":"Karthik","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16271"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"ref19","article-title":"Data roaming and early fusion for composed image retrieval","author":"Levy","year":"2023","journal-title":"arXiv preprint"},{"issue":"3","key":"ref20","first-page":"7","article-title":"Data roaming and early fusion for composed image retrieval","volume":"2","author":"Levy","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Blip2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","first-page":"2125","article-title":"Image retrieval on real-life images with pretrained vision-and-language models","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Liu","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00673"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01850"},{"key":"ref27","article-title":"Rtic: Residual learning for text and image composition using graph convolutional network","author":"Shin","year":"2021","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02540"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28334"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref35","article-title":"Clip-vip: Adapting pretrained image-text model to video-language representation alignment","author":"Xue","year":"2022","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01136"},{"key":"ref37","article-title":"Curlingnet: Compositional learning between images and text for fashion iq data","author":"Yu","year":"2020","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445947.pdf?arnumber=11445947","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:32:53Z","timestamp":1777613573000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445947\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01900","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}